视觉基础模型能否导航？零样本真实世界评估与经验教训
Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned
AI总结：
本文对五种视觉导航模型在真实环境中进行零样本评估，发现其存在几何理解不足、感知混淆和分布漂移等系统性问题，并公开评估代码与数据集。
摘要：
视觉导航模型（VNMs）通过从大规模视觉演示中学习，有望实现通用化的机器人导航。尽管在真实世界部署日益增多，现有评估几乎完全依赖成功率（机器人是否到达目标），这掩盖了轨迹质量、碰撞行为以及对环境变化的鲁棒性。我们针对五种最先进的VNMs（GNM、ViNT、NoMaD、NaviBridger和CrossFormer）在两个机器人平台和五个室内外环境中进行了真实世界评估。除了成功率，我们结合了基于路径的指标与基于视觉的目标识别分数，并通过受控图像扰动（运动模糊、太阳眩光）评估鲁棒性。我们的分析揭示了三个系统性问题：(a) 即使是架构复杂的扩散和Transformer模型也频繁发生碰撞，表明几何理解有限；(b) 模型无法区分感知相似但存在语义差异的不同位置，导致在重复环境中出现目标预测错误；(c) 在分布偏移下性能下降。我们将公开发布评估代码和数据集，以促进VNMs的可重复基准测试。
英文摘要：
Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations. Despite growing real-world deployment, existing evaluations rely almost exclusively on success rate, whether the robot reaches its goal, which conceals trajectory quality, collision behavior, and robustness to environmental change. We present a real-world evaluation of five state-of-the-art VNMs (GNM, ViNT, NoMaD, NaviBridger, and CrossFormer) across two robot platforms and five environments spanning indoor and outdoor settings. Beyond success rate, we combine path-based metrics with vision-based goal-recognition scores and assess robustness through controlled image perturbations (motion blur, sunflare). Our analysis uncovers three systematic limitations: (a) even architecturally sophisticated diffusion and transformer-based models exhibit frequent collisions, indicating limited geometric understanding; (b) models fail to discriminate between different locations that are perceptually similar, however some semantics differences are present, causing goal prediction errors in repetitive environments; and (c) performance degrades under distribution shift. We will publicly release our evaluation codebase and dataset to facilitate reproducible benchmarking of VNMs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
